phi-1.5_base: benchmark results
Provider: Microsoft.
Aggregate Rating 1262 ± 36, rank #9151 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 16.53 | Accuracy (%) (5-shot) | 38.1 |
| Open LLM Leaderboard v1 - ARC Challenge | 50.26 | Normalized accuracy (%) (25-shot) | 24.6 |
| Open LLM Leaderboard v1 - WinoGrande | 69.38 | Accuracy (%) (5-shot) | 23.4 |
| Open LLM Leaderboard v1 - MMLU | 39.34 | Accuracy (%) (5-shot) | 20.7 |
| Open LLM Leaderboard v1 - HellaSwag | 61.2 | Normalized accuracy (%) (10-shot) | 15.2 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 39.71 | MC2 (%) (0-shot) | 11.7 |
Interactive version: theaggregate.ai/model?slug=phi-1-5-base · How It Works · Data refreshed daily, snapshot 2026-11-08.